Yunhao (Andy) Ge 葛云皓 CS Ph.D. Candidate @ University of Southern California Student Researcher @ Google Cloud AI Department of Computer Science @ University of Southern California Email: yunhaoge at usc dot edu     [About Me] [News & Updates] [Publications] [Experience]

About Me

I am now a Ph.D. Candidate in the Department of CS at University of Southern California (USC) and a member of iLab, working with Prof. Laurent Itti. I'm also currently a student researcher at Google Cloud AI working with Dr. Sercan Arik and Dr. Jinsung Yoon . I also work closely with Dr. Ziyan Wu ( UII America ) and Dr. Vibhav Vineet ( Microsoft Research ).

• Causal Explainable AI ((1) Understanding reasoning logic and causality of Neural Networks (NN) (2) Use explanation as feedback to help improve the performance of the original NN.)
• Understanding AI models beyond accuracy (disentangled representation learning, human-NN knowledge exchange, steerability, generalization, domain adaptation, and bias)
• Humanoid Neural Network (simulating human cognitive learning ability (Imagination, Reasoning, Visual Recognition, Continual Learning) by using various learning algorithms (Generative models, Representation Learning, Graph Neural Network, etc.)

Research opportunities: I am happy to collaborate and/or answer questions about my research and USC academic programs. If you are interested, please send me an email. I especially encourage USC master students who want to involve exciting projects targeting top-tier conferences/journals to reach out.

News & Updates

[2022/01/20] Finally passed my qual exam and officially became a PhD Candidate now.

[2021/08/23] I will be joining Google Cloud AI as a student researcher, advised by Dr. Sercan Arik and Dr. Jinsung Yoon

[2021/07/15] USC News , Tech Xplore , Technology Networks and other media pressed our ICLR 2021 paper: Group-Supervised Learning (Enabling the 'imagination' of artificial intelligence)

[2021/05/17] I will be joining Computer Vision Group at Microsoft Research Redmond as a research intern in summer 2021, advised by Dr. Vibhav Vineet and Dr. Neel Joshi

[2021/05/08] Serving as a reviewer for NeurIPS 2021 and ICLR 2022!

[2021/04/07] Releasing Img2SceneGraph, a pipeline that transfers images to scene graphs with node attributes! Welcome to Download and try!

[2021/04/02] One paper (Graph Autoencoder for Graph Compression and Representation Learning) was accepted by Neural Compression Workshop @ICLR 2021 as Spotlight!

[2021/02/28] One paper (A Peek Into the Reasoning of Neural Networks: Interpreting with Structural Visual Concepts) was accepted by CVPR 2021!

[2021/01/16] One paper (Beneficial Perturbation Network for designing general adaptive artificial intelligence systems) was accepted by TNNLS!

[2021/01/12] One paper (Zero-shot Synthesis with Group-Supervised Learning) was accepted by ICLR 2021!

[2020/09/14] Fonts dataset was proposed for fast testing and idea iteration on disentangled representation learning and zero-shot synthesis. Welcome to Download and try!

[2020/07/02] One paper (Pose Augmentation: Class-agnostic Object Pose Transformation) was accepted by ECCV 2020!

[2020/05/12] I will be joining UII America as a research intern in summer 2020, advised by Dr. Ziyan Wu and Dr. Srikrishna Karanam

[2019/08/12] I will be joining USC CS Ph.D. Program in fall 2019, advised by Prof. Laurent Itti.

[2019/07/01] One paper (Synthesis and inpainting-based MR-CT registration) was accepted by MICCAI 2019.

[2019/03/01] One paper (Unpaired Whole-Body Mr to CT Synthesis) was accepted by ISBI 2019.

Selected Publications [Google Scholar]

	A Peek Into the Reasoning of Neural Networks: Interpreting with Structural Visual Concepts TL;DR: Takes a step towards mimicking the reasoning process of NNs and provide logical, concept-level explanations for final model decisions. Yunhao Ge, Yao Xiao, Zhi Xu, Meng Zheng, Srikrishna Karanam, Terrence Chen, Laurent Itti and Ziyan Wu IEEE/ CVF International Conference on Computer Vision and Pattern Recognition (CVPR), 2021. [paper] [github] [website] [video] [知乎] [机器之心] [AI科技评论]
	Zero-shot Synthesis with Group-Supervised Learning TL;DR: Using Controllable disentangled representation learning to simulate human knowledge factorization for imagination Yunhao Ge, Sami Abu-El-Haija, Gan Xin and Laurent Itti International Conference on Learning Representations (ICLR), 2021. [paper] [code] [website] [Fonts Dataset] [USC Viterbi Press] [知乎] [AI科技评论] [ USC News ] [ Tech Xplore ] [ Technology Networks ]
	Encouraging Disentangled and Convex Representation with Controllable Interpolation Regularization TL;DR: A simple yet efficient method: Controllable Interpolation Regularization (CIR), which creates a positive loop where the disentanglement and convexity can help each other Yunhao Ge, Zhi Xu, Yao Xiao, Gan Xin, Yunkui Pang and Laurent Itti arXiv, 2021. [paper]
	Graph Autoencoder for Graph Compression and Representation Learning TL;DR: Multi-kernel Inductive Attention Graph Autoencoder (MIAGAE) utilizes the node similarity and graph structure to compress all nodes and edges as a whole. Yunhao Ge*, Yunkui Pang*, Linwei Li and Laurent Itti (*=equal contribution) Neural Compression: From Information Theory to Applications--Workshop@ (ICLR), 2021. [paper] [code] [Img2SceneGraph] Spotlight Presentation
	Pose Augmentation: Class-agnostic Object Pose Transformation for Object Recognition TL;DR: Eliminate-add generator to explicitly disentangle pose from object identity by maximizing pose entropy Yunhao Ge, Jiaping Zhao, Laurent Itti European Conference on Computer Vision (ECCV), 2020. [paper] [github] [video-1min] [video-10min]
	Beneficial Perturbation Network for designing general adaptive artificial intelligence systems TL;DR:Allowing a single network to learn potentially unlimited parallel input to output mappings, and to switch on the fly between them at runtime. Shixian Wen, Amanda Rios*, Yunhao Ge* and Laurent Itti (*=equal contribution) IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2021. [paper]
	Unpaired MR to CT Synthesis with Explicit Structural Constrained Adversarial Learning Yunhao Ge*, Dongming Wei*, Zhong Xue, Yiqiang Zhan, Xiang Zhou, Qian Wang and Shu Liao (*=equal contribution) IEEE International Symposium on Biomedical Imaging (ISBI), 2019. [paper] [code]
	Synthesis and inpainting-based MR-CT registration for image-guided thermal ablation of liver tumors Dongming Wei, Sahar Ahmad, Jiayu Huo, Wen Peng, Yunhao Ge, Zhong Xue, Pew-Thian Yap, Wentao Li, Dinggang Shen, Qian Wang International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2019. [paper]
	Unpaired Whole-body MR to CT Synthesis with Correlation Coefficient Constrained Adversarial Learning Yunhao Ge, Zhong Xue, Yiqiang Zhan, Xiang Zhou and Shu Liao SPIE-Medical Imaging (SPIE), 2019. [paper] [code] Oral Presentation

Intern & Work Experience

Google Cloud AI, Mountain View, USA (Aug. 2021 - current)

• Position: Student Researcher in Google Cloud AI
• Supervisor: Sercan Arik and Dr. Jinsung Yoon
• Project: Causal Explainable AI

Microsoft Research, Redmond, USA (May. 2021 - Aug. 2021)

• Position: Research Intern in Computer Vision Group
• Supervisor: Dr. Vibhav Vineet and Dr. Neel Joshi
• Project: On-demand training data generation with Neural Rendering --> submitted to CVPR 2022

UII America, Inc, Boston, USA (May. 2020 - Aug. 2020)

• Position: Research Intern in UII America
• Supervisor: Dr. Ziyan Wu and Dr. Srikrishna Karanam
• Project: Explain reasoning logic of NN --> CVPR 2021

Flexiv Ltd, Shanghai, China (May. 2019 - Aug. 2019)

• Position: Computer Vision Engineer in Flexiv Robotics
• Supervisor: Prof. Cewu Lu and Dr. Shuyun Chong
• Project: Robotics adaptive massage based on human pose detection and tracking

United Imaging Intelligence Co., Ltd, Shanghai, China (Jun. 2018 - Apr. 2019)

• Position: Research Intern in United Imaging Intelligence
• Supervisor: Prof. Dinggang Shen and Dr. Shu Liao
• Project: Unpaired MR to CT image synthesis --> ISBI 2019 MICCAI 2019

Scholarships

• Aug 2019 Annenberg Graduate Fellowship at University of Southern California
• Sep 2017 National Scholarship(Graduate), (highest honor for graduates) top 1% nationwide
• Sep 2015 National Scholarship(Undergraduate), (highest honor for undergraduates, top 2% nationwide)
• May 2018 KaiYuan Motivational Scholarship top 0.5% in Shanghai Jiao Tong University
• Sep 2015 Presidential Scholarship, (highest honor in Shandong University) top 0.2% in Shan Dong University
• Sep 2015 BaoGang Excellent student Scholarship, (4 Places per year at Shandong University)
• Sep 2015 & Sep 2014 & Sep 2015 First Prize Scholarship (Top 6% in China,three-year continuous)

Honors and Awards

• Aug 2017 The First Prize 2017 ROBOMASTER The World’s Leading Robotics Competition (Responsible for the design of electronic control in robotics)[Code-T_Infantry]
• Aug 2017 Rank 1st (preliminary competition) , Tianchi: Precision medical competition-Artificial Intelligence Aided genetic risk prediction of diabetes [Code-Pred_diabetes]
• Oct 2015 The First Prize 9th international college students ican innovation and entrepreneurship contest
• Oct 2015 The Special prize(Top 1%) 6th National University Students Process Equipment Practice and Innovation Competition
• Aug 2015 The Silver prize 8th national college students in energy saving social practice and science and technology competition

Academic Service

Software & Patents

	Systems and methods for image processing S Liao, GE Yunhao, WEI Dongming US Patent App. 16/729,303.
	Pulmonary Nodular Assisted Detection System Based on AI(V1.0) Bin Li, Yunhao Ge 2018SR037095.
	A Two-Layer Barrier Free Parking Equipment Based on Bionic Manipulator Yunhao Ge, Shangze Yang, Zheng Zhang, Weixin Yan and Yanzheng Zhao CN201610712048.
	A Double Decker Parking Equipment based on Shear Lifting Mechanism and Hydraulic Mechanism Yunhao Ge, Xulong Zhou, Peng Liu and Yanzheng Zhao CN201610704408.

Last update: Jan. 21, 2022